{"id":"https://openalex.org/W2891226622","doi":"https://doi.org/10.21437/avsp.2017-13","title":"Exploring ROI size in deep learning based lipreading","display_name":"Exploring ROI size in deep learning based lipreading","publication_year":2017,"publication_date":"2017-08-25","ids":{"openalex":"https://openalex.org/W2891226622","doi":"https://doi.org/10.21437/avsp.2017-13","mag":"2891226622"},"language":"en","primary_location":{"id":"doi:10.21437/avsp.2017-13","is_oa":false,"landing_page_url":"https://doi.org/10.21437/avsp.2017-13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 14th International Conference on Auditory-Visual Speech Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055069331","display_name":"Alexandros Koumparoulis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandros Koumparoulis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064636177","display_name":"Youssef Mroueh","orcid":"https://orcid.org/0000-0001-8798-1267"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youssef Mroueh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088753951","display_name":"Steven J. Rennie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven J. Rennie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6216,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92683575,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"64","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7251216173171997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5975344777107239},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5270828604698181},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.505198061466217},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3580007553100586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251216173171997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5975344777107239},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5270828604698181},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.505198061466217},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3580007553100586}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/avsp.2017-13","is_oa":false,"landing_page_url":"https://doi.org/10.21437/avsp.2017-13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 14th International Conference on Auditory-Visual Speech Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:ir.lib.uth.gr:11615/75304","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/75304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400243","display_name":"University of Thessaly Institutional Repository (University of Thessaly)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145722265","host_organization_name":"University of Thessaly","host_organization_lineage":["https://openalex.org/I145722265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"14th International Conference on Auditory-Visual Speech Processing, AVSP 2017","raw_type":"conferenceItem"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W196476531","https://openalex.org/W581956982","https://openalex.org/W1503933356","https://openalex.org/W1518556865","https://openalex.org/W1536680647","https://openalex.org/W1586532344","https://openalex.org/W1600744878","https://openalex.org/W1677182931","https://openalex.org/W1861390992","https://openalex.org/W2055098062","https://openalex.org/W2060510034","https://openalex.org/W2064675550","https://openalex.org/W2076462394","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2115353073","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2136155248","https://openalex.org/W2146502635","https://openalex.org/W2184188583","https://openalex.org/W2267805933","https://openalex.org/W2293829681","https://openalex.org/W2398406965","https://openalex.org/W2407414360","https://openalex.org/W2511073133","https://openalex.org/W2530876040","https://openalex.org/W2533523411","https://openalex.org/W2547418827","https://openalex.org/W2561086211","https://openalex.org/W2572911620","https://openalex.org/W2578229578","https://openalex.org/W2604769302","https://openalex.org/W2612754342","https://openalex.org/W2949117887","https://openalex.org/W2952746495","https://openalex.org/W2963192365","https://openalex.org/W2963528589","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W3009238340","https://openalex.org/W2755342338"],"abstract_inverted_index":{"Automatic":[0],"speechreading":[1,132],"systems":[2,17],"have":[3],"increasingly":[4],"exploited":[5],"deep":[6,59],"learning":[7,60],"advances,":[8],"resulting":[9,54],"in":[10,86,119,155],"dramatic":[11],"gains":[12],"over":[13],"traditional":[14],"methods.":[15],"State-of-the-art":[16],"typically":[18],"employ":[19,90],"convolutional":[20],"neural":[21],"networks":[22],"(CNNs),":[23],"operating":[24],"on":[25,52,76,110,191],"a":[26,70,91,111,144,148,163,171],"video":[27],"region-of-interest":[28],"(ROI)":[29],"that":[30,83,126,146],"contains":[31,147],"the":[32,44,53,58,103,135,152,159,168,179,184],"speaker\u2019s":[33],"mouth.":[34],"However,":[35],"little":[36],"or":[37],"no":[38],"attention":[39],"has":[40],"been":[41],"paid":[42],"to":[43,94,143,157,177],"effects":[45],"of":[46,114,151],"ROI":[47,104,127,145],"physical":[48],"coverage":[49],"and":[50,78,98,161],"resolution":[51],"recognition":[55,73],"performance":[56,133],"within":[57],"framework.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,84,89],"investigate":[66],"such":[67],"choices":[68,129],"for":[69],"visual-only":[71,137],"speech":[72],"system":[74],"based":[75],"CNNs":[77],"long":[79],"short-term":[80],"memory":[81],"models":[82],"present":[85],"detail.":[87],"Further,":[88],"separate":[92],"CNN":[93],"perform":[95],"face":[96,182],"detection":[97],"facial":[99],"landmark":[100],"localization,":[101],"driving":[102],"extraction":[105],"process.":[106],"We":[107],"conduct":[108],"experiments":[109],"multi-speaker":[112],"corpus":[113],"connected":[115],"digits":[116],"utterances,":[117],"recorded":[118],"ideal":[120],"visual":[121],"conditions.":[122],"Our":[123],"results":[124],"show":[125],"design":[128],"affect":[130],"automatic":[131],"significantly:":[134],"best":[136],"word":[138],"error":[139,174],"rate":[140],"(5.07%)":[141],"corresponds":[142],"large":[149],"part":[150],"lower":[153,181],"face,":[154],"addition":[156],"just":[158],"mouth,":[160],"at":[162],"relatively":[164],"high":[165],"resolution.":[166],"Noticeably,":[167],"result":[169],"represents":[170],"27%":[172],"relative":[173],"reduction":[175],"compared":[176],"employing":[178],"entire":[180],"as":[183],"ROI.":[185],"\u00a9":[186],"2017":[187],"14th":[188],"International":[189],"Conference":[190],"Auditory-Visual":[192],"Speech":[193],"Processing,":[194],"AVSP":[195],"2017.":[196],"All":[197],"rights":[198],"reserved.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2018-09-27T00:00:00"}